Joint Learning of Pre-Trained and Random Units for Domain Adaptation in Part-of-Speech Tagging

Sara Meftah, Youssef Tamaazousti, Nasredine Semmar, Hassane Essafi, Fatiha Sadat


Abstract
Fine-tuning neural networks is widely used to transfer valuable knowledge from high-resource to low-resource domains. In a standard fine-tuning scheme, source and target problems are trained using the same architecture. Although capable of adapting to new domains, pre-trained units struggle with learning uncommon target-specific patterns. In this paper, we propose to augment the target-network with normalised, weighted and randomly initialised units that beget a better adaptation while maintaining the valuable source knowledge. Our experiments on POS tagging of social media texts (Tweets domain) demonstrate that our method achieves state-of-the-art performances on 3 commonly used datasets.
Anthology ID:
N19-1416
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4107–4112
Language:
URL:
https://aclanthology.org/N19-1416
DOI:
10.18653/v1/N19-1416
Bibkey:
Cite (ACL):
Sara Meftah, Youssef Tamaazousti, Nasredine Semmar, Hassane Essafi, and Fatiha Sadat. 2019. Joint Learning of Pre-Trained and Random Units for Domain Adaptation in Part-of-Speech Tagging. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4107–4112, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Joint Learning of Pre-Trained and Random Units for Domain Adaptation in Part-of-Speech Tagging (Meftah et al., NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/N19-1416.pdf
Video:
 https://vimeo.com/361815756
Data
Tweebank